GPT-4.1 nano
OpenAI
OpenAI's cheapest and fastest model in the GPT-4.1 family (April 2025), built for high-volume classification, extraction, and autocomplete where sophisticated reasoning isn't needed. Retains the 1M-token context window at the lowest price in the lineup.
Strengths
- OpenAI's cheapest and fastest model
- Full 1M-token context window
- Ideal for classification, extraction, and autocomplete
- Very low latency at high volume
Caveats
- Not suited to sophisticated reasoning or complex coding
- 32K max output
- Quality trails larger GPT-4.1 tiers
- Vendor
- OpenAI
- Context Window
- 1,000,000 tokens
- Max Output
- 32,768 tokens
- License
- Proprietary
- Release Date
- 2025-04-14
- Modalities
- textimage
Capabilities
Vision
Audio
Video
Tool Use
Resources
Pricing
$0.10 per 1M input tokens, $0.40 per 1M output tokens - OpenAI's cheapest and fastest model. 1M-token context window.